Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

PLAYER-CENTRIC ADAPTATION IN EDUCATIONAL VIDEO GAMES

286 views

Published on

In recent decades, video games have proved not only as entertainment media, which develops intellectual and social skills, but also as a mean for technology-supported learning. Both serious and entertainment ames apply effective methods to adapt the gaming process to the characteristics of individual players. This presentation discusses a comprehensive player model used for dynamic adaptation of mechanics, dynamics and audio-visual parameters of the game. Player´s emotions and attention are determined during the game by analyzing facial expressions and skin conductivity, while the style of playing is determined implicitly based on monitoring of selected metrics characterizing the gaming process. These features of the player are used for dynamic and personalized control of the adaptation of the game, leading to greater involvement and interest in playing learning games, and hence - to better performance and usability of the game
The presented results are achieved within the project ADAPTIMES (ADAPTIve player-centric serious video gaMES), FP7 PEOPLE, Marie Curie Actions.

Published in: Education
  • Be the first to comment

PLAYER-CENTRIC ADAPTATION IN EDUCATIONAL VIDEO GAMES

  1. 1. PLAYER-CENTRIC ADAPTATION IN EDUCATIONAL VIDEO GAMES Boyan Bontchev Prof. at Dep. of Software Technologies, Fac. of Mathematics and Informatics, Sofia Univ., Bulgaria Marie Curie Fellow at Brainstorm Multimedia, Spain
  2. 2. Agenda Introduction Problems of player-centric adaptation in video games The ADAPTIMES player model Dynamic adaptation process using player performance, affect and playing styles Case study 1 - the “Rush for Gold” emotionally adaptive game Results Case study 2 – adaptive educational maze/quiz/zoom games Conclusions and future works 2 15/06/2016 Player-centric adaptation in educational video games IMI-BAS’2016
  3. 3. Player-centric adaptation Player-centric adaptation in video games needs to answer some questions: Who – player character structural and behavioral changes => requires player modelling How – how adaptation will be realized => requires adaptive loop design What – which game features can be adapted => requires adaptive gameplay design Why – advantages of game adaptation => requires analysis of outcomes in playability and learning results 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 3
  4. 4. Player modelling Player modelling is crucial for realization of an effective player-centric adaptation in both applied and entertainment video games. It implies: Observation of individual player’s behavior “from a contextually omniscient view” Construction and updates of a model of that player based on observation, and Intelligent game adaptation for tailoring the gameplay to the individual player. 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 4  Source: Magerko, B. Adaptation in Digital Games, COMPUTER, July 2008, pp.87-89.
  5. 5. The ADAPTIMES FP7 project  ADAPTIve player-centric serious video gaMES  ADAPTIMES aims at investigating how cognitive abilities (the cognitive part), psycho-emotional status (the affective part) and playing style (the conative part – that of “desire, volition, and striving”)  can be used in a holistic approach for efficient and effective player-centric adaptation 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 5
  6. 6. Adaptation Model 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 6 Game dynamics Player Player style metrics Playing styles Performance and efficiency (abilities, skills and knowledge) Emotions (flow, immersion & intrinsic motivation)
  7. 7. Flow mental state as function of challenge and player’s ability/skills (Csikszentmihalyi, 1997) 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 7 LowChallenge/ComplexityHigh Individual average Anxiety Arousal Flow Worry Apathy Boredom Relaxation Low Skills High Control
  8. 8. Measuring process Measuring player’s performance – by tracking player’s results, incl. time, task difficulties and efficiency Measuring playing styles – based on tracking specific gaming metrics describing player’s style of playing Measuring player’s affect (emotions and arousal): By means of analysis of psychophysiology signals (arousal) By means of visual expressions analysis (emotional states) 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 8
  9. 9. Affect inferred by psychophysiology signals EDA (Electro-Dermal Activity) Custom EDA meter – custom hardware device and software (H2020 RAGE asset developed by SU) 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 9
  10. 10. Emotions inferred by visual expressions analysis Custom emotion recognizer using Affectiva SDK Recognizes: sadness, disgust, anger, surprise, fear, joy; engagement, attention (fixation), eye closures (saccades) 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 10
  11. 11. Workflow of emotion-based game dynamic adaptation control 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 11 Implicit Emotional Indicators (via sensors & other devices) Facial expr. GSR Heart Rhythm ECG EEG Pressure … Change Procedures Time Velocity Acceleration Route Size Defeat range Luminosity Contrast … Real-Time Explicit Player Feedback through Adaptation Control Panel Analysis Change Visuali- zation Triggering Events on Behavior Templates
  12. 12. In-Game Explicit Player Feedback using a built-in Adaptation Control Panel 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 12
  13. 13. Playing style vs learning style Playing style - persistent traits of the player, whereas defined play styles as treating “motivations as a more temporary state, with an implication that players may adopt different play styles in different games or at different times”. (Magerko et al., 2008) Learning style – “characteristic cognitive, effective, and psychosocial behaviors that serve as relatively stable indicators of how learners perceive, interact with, and respond to the learning environment”. (Curry, 1981) 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 13
  14. 14. Playing style models 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 14 Relationships between Honey and Mumford (1982) learning styles and playing styles of ADOPTA (Aleksieva et al., 2011) and Bartle (1996) Honey and Mumford Learns/plays by: ADOPTA Bartle Activist Hand–eye coordination, planning and strategizing, problem-solving, teamwork and the ability to think quickly Competitor Killer Theorist Logically entering problems step-by-step, with spatial awareness and verbal & numeracy skills Logician Achiever Pragmatist Planning, decision-making, testing hypotheses, strategic thinking, management skills Strategist Explorer Reflector Observing and watching reflectively Dreamer Socializer
  15. 15. Player style measurement Explicitly - though self-report A 40 items questionnaire for measuring Competitor, Dreamer (Discoverer), Logician and Strategist style of playing To be experimented together with the 40 items questionnaire for measuring Honey and Mumford learning styles Implicitly - during game time of playing specific mini- game Based on player’s metrics for specific game tasks including performance (result), efficiency (result/effort), task difficulty and play time Linear regression coefficients determined by: qualitative study (structured interviews with gamers) least squares method 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 15
  16. 16. Adaptable game features 1/3 1. Adaptive automation of game tasks (and feedback for next experiments): A.1 Game-driven tasks:  explicit tasks - game objectives (to shoot/discover gold bullions or to solve puzzles) adapt to the gameplay;  implicit tasks - not explicitly stated by the game interface but expected to be fulfilled:  maximize your skills in shooting, discovering, solving and strategic planning of activities  collect as many gold bullions as possible A.2 Player-driven tasks - created by the player thanks to his/her creativity within existing limitations of given game mechanics and leading to so called emergent gameplay  how to find best position for shooting (depends on gun high and shooting angle)  how to explore the temple with changing visual properties 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 16
  17. 17. Adaptable game features 2/3 2. Dynamic Difficulty Adjustment (DDA):  DDA by means of automatic level generation - uses methods for procedural content generation Logic puzzles have increasing dynamically their difficulty with higher player results and vice versa  DDA by means of adjusting level content, i.e. game items for player interactions – means dynamic adaptation of level of inventory interacted by the player for specific game context, according to player’s skill acquisition: Hidden billions are more difficult to be found with player progress and higher affect (they are moved to more hidden places) Flying bullions change velocity & acceleration plus striking force - changed with player efficiency as well with player´s emotions 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 17
  18. 18. Adaptable game features 3/3 3. Adaptation of audio-visual effects: according player´s affect (both emotions and arousal) using thresholds of happiness, fear, surprise and disgust level, there are adapted : ambient illumination change focus and contrast of game objects such as puzzle panels, buttons, gold bullions, statues, etc. the volume of sound 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 18
  19. 19. Methodology – case study 1 Experiment 1 – by playing an affectvely adapted action 3D video game, to try to:  Recognize individual playing style using specific game metrics and compare it to the style measured by self-report:  Demographic data and former playing experience – 13 items  Playing style – 40 items  Learning style – 40 items  Big Five personality traits (openness to experience, conscientiousness, extraversion, agreeableness, and neuroticism) – 10 items (for further study)  Emotional adaptation – 5 questions  Find correlations between the playing style and learning style  Explore the effect of affect-based adaptations of content generation, DDA and audio-visual effects over:  preference to play the game  player´s performance and efficiency  difficulty of solved task 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 19
  20. 20. Case study 1 – Rush for Gold game  A 3D video game using adaptation based on player performance, efficiency and emotional state using the FACE web service of SightCorp (https://face.sightcorp.com/)  Developed by using Brainstorm eStudio (http://www.brainstorm.es/products/estudio/)  Allows implicit recognition of ADOPTA playing styles in order to validate them to ones calculated by using self-report. The implicitly found style will be used for automatic selection of learning content appropriate to that style.  Goal: to collect 12 bars of gold (bullions), which are flying, hidden or inside logic puzzles needed to be solved, all located in a 3D Egypt temple with enhanced audio-visual effects being object of adaptation, as well.  The player can use a Strategy Planning Table (SPT):  represents a table with three rows for planning numbers of bars of the three groups available in the game  contains data about average effectivity of performance for collecting the gold bars of each group useful for building a strategy for optimal way of play. 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 20
  21. 21. Rush for Gold 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 21
  22. 22. Player style measurement Implicitly during play time of specific mini-game Based on player’s metrics for specific game tasks: Performance (result) Efficiency (result/effort) Task difficulty Play time SMT updates & views (for Strategists) 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 22 Rush For Gold, part 2 - https://www.youtube.com/ watch?v=aJe61bUDE40
  23. 23. Emotion-based adaptation in Rush for Gold The game adaptation control is at run time and implicit for the player The adaptation control makes the video game aligned to specific response patterns of individual players for bringing positive effect on playability and learning outcomes The adaptation process runs in the context of the game and aligns adaptable game features to player-centric metrics showing: player’s progress and performance player’s emotions –inferred by face expression analysis fear, surprise, sadness and disgust are applied for additional correction of current difficulty of shooting and discovering tasks by using specific thresholds of their levels when finding relatively high fear, sadness and surprise, task difficulty is decreased, while the opposite occurs in cases of high level of disgust 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 23
  24. 24. Experiment (FMI-SU, March 2016) Executed at Sofia University, Bulgaria, with 34 volunteers (average aged 27, SD=10; 18 men and 16 women) They passed group explanation and demonstration (20 min.), procedure of informed consent (translated in Bulgarian, 15 min.), individual assisted trial (5 min.) and, finally, unassisted game session to determine their style of play (15-20 min.). Half of the volunteers (N=17) played the game with emotional adaptation switched on (forming the experimental group), unlike the others (the control group). 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 24
  25. 25. Results about preference to play with emotion-based adaptation The quiz reveals (five-level Likert scale from 1 to 5): certain preference to play the game with emotion-based adaptation (question Q1 average=3.9, sd=1.1) positive appreciation of that adaptation of shooting difficulty (Q2 average=4.0, sd=0.8) the same for discovering difficulty (Q3 average=3.8, sd=0.7), and brightness and contrast (Q4 average=4.1, sd=0.7). Statistically significant correlations between preference to play with emotion-based adaptation and some game metrics 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 25
  26. 26. Results about preferences to play with emotional adaptation Positive statistically significant correlations (0,34÷0,55) between:  preferences to play with emotional adaptation and shooting/discovering efficiency, discovering performance and game session time reveal the beneficial impact of emotional adaptation inside the experimental group. 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 26
  27. 27. Results about audio-vidual adaptations 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 27 Adapted brightness and contrast are correlated: positively to solving performance (because of attracting player’s attention to the puzzles) and negatively to discovering performance (because of attracting player’s attention to other objects)
  28. 28. Results about playing styles Explicitly measured though self-report 40 item questionnaire for measuring Competitor (C), Dreamer (Discoverer, D), Logician (L) and Strategist (S) style of playing – filled by 312 subjects, Cronbach alpha 0.527, 0.557, 0.711 and 0.572. High correlations (r=0.806, 0.778, 0.879, 0.619; p<0.01) between these playing styles and Honey and Mumford learning styles Implicitly during game time of playing specific mini-game For playing styles found by linear regression using player´s metrics and coefficients found by qualitative study (structured interviews with gamers) – high correlations with self-report styles (r=0.802, 0.779, 0.873, 0.633 for C, D, L and S styles; p<0.001) For regression model coefficients estimated by the least squares method – higher correlations with self-reported styles (r=0.827; 0.792; 0.882; 0.713 for C, D, L and S styles; p<0.001) 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 28
  29. 29. Methodology – case study 2 Experiment 2 – by playing an action 3D video game for recognition of playing styles and, next, educational games with learning content adapted both to styles and affect of the player, plus questionnaires about:  Demographic data – 5 items  Playing style – 40 items  Game engagement questionnair (GEQ) – 19 items  Attention, relevance, confidence, and satisfaction (ARCS) questionnair – 15 items – all applied for: Enhanced recognition of individual playing style using specific game metrics and compare it to the style measured by self-report Explore the effect of affect-based adaptation over: player´s engagement and attention learning outcomes Preference of adaptation control – adaptation strenght and affective feedback direction 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 29
  30. 30. 30 Rush For Gold (playing style found) 15/06/2016 STRAMAG generated labyrinth (maze game) 3D quiz game (assessment) 3D zoom puzzle Player-centric adaptation in educational video games IMI-BAS’2016 Game sequence
  31. 31. Case study 2 (June, 2016) 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 31 Brainstorm eStudio Rush for Gold STRAMAG maze 3D quiz assessment 3D zoom ordering Rooms RoomsRooms Rooms RoomsTunnels Affectiva SDK Emotion recognizer RAGE arousal asset RAGE arousal asset.NET USB TCP sockets
  32. 32. A platform for generation of customizable video maze games for education 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 32 Maze Editor Transitions table Property Editor Titles … Texts … Graphics … Python Scripts Brainstorm API 3D Maze Game Engine Brainstorm Run Time Environment Embedded Mini-Games 3D video game Property Metadata Graph Editor
  33. 33. STRAMAG (STRAtegic MAnagement Game) 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 33
  34. 34. Conclusions 1/2 Player-centric adaptive game play possesses essential advantages compared to the non-adaptive gameplay The synergy of using player´s performance, emotions, and playing styles is very promising All they are identified at run time and used for adapting game mechanics, dynamics and audio-visual content, in a dynamic and implicit way. 34 15/06/2016 Player-centric adaptation in educational video games IMI-BAS’2016
  35. 35. Conclusions 2/2 The results reveal a promising and positive appreciation of emotion-based adaptation and, as well, interesting statistically significant correlations between such adjusting of dynamic difficulty of tasks and player´s self- report. More experiments with real time player´s feedback on adaptation use, additional self-reporting and qualitative analyses are needed for revealing how such emotion- based adaptations affect game experience and playability, learning outcomes and consequences of flow 35 15/06/2016 Player-centric adaptation in educational video games IMI-BAS’2016
  36. 36. Future work Emotionally-adaptive games and other software app’s Dynamic adaptation control Software app’s using user affectation: HRV TEMP Web-based platforms for generation of educational games targeted to non-ICT people Semantic content management in applied games 15/06/2016Player-centric adaptation in educational video games IMI-BAS’2016 36
  37. 37. Thank you for your attention! Discussion Videos at: https://www.youtube.com/watch?v=rSzM2RrceNw&index=1&li st=PLs4ZK9XAjRxpROiCNQ1kdDR8SFpH-itmY More info at: http://adaptimes.eu/ 37 15/06/2016 Player-centric adaptation in educational video games IMI-BAS’2016

×